홈 › Papers

RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation

2025-09-19 · Chao Yu, Yuanqing Wang, Zhen Guo, Hao Lin, Si Xu, Hongzhi Zang, Quanlu Zhang, Yongji Wu, Chunyang Zhu, Junhao Hu, Zixiao Huang, Mingjie Wei, Yuqing Xie, Ke Yang, Bo Dai, Zhexuan Xu, Jiakun Du, Xiangyuan Wang, Xu Fu, Letong Shi, Zhihao Liu, Kang Chen, Weilin Liu, Gang Liu, Boxun Li, Jianlei Yang, Zhi Yang, Guohao Dai, Yu Wang arxiv

Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workflows often lead to low hardware utilization and slow training on existing systems. In this paper, we present RLinf, a high-performance RL training system based on our key observation that the major roadblock to efficient RL training lies in system flexibility. To maximize flexibility and efficiency, RLinf is built atop a novel RL system design paradigm called macro-to-micro flow transformation (M2Flow), which automatically breaks down high-level, easy-to-compose RL workflows at both the temporal and spatial dimensions, and recomposes them into optimized execution flows. Supported by RLinf worker's adaptive communication capability, we devise context switching and elastic pipelining to realize M2Flow transformation, and a profiling-guided scheduling policy to generate optimal execution plans. Extensive evaluations on both reasoning RL and embodied RL tasks demonstrate that RLinf consistently outperforms state-of-the-art systems, achieving $1.07\times-2.43\times$ speedup in end-to-end training throughput.

📄 PDF Abstract BibTeX arXiv:2509.15965

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

2025-10-08 · Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu 외 arxiv

Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through i…

Reinforcement Learning

Flexible Multiple-Objective Reinforcement Learning for Chip Placement

2022-04-13 · Fu-Chieh Chang, Yu-Wei Tseng, Ya-Wen Yu, Ssu-Rui Lee 외

Recently, successful applications of reinforcement learning to chip placement have emerged. Pretrained models are necessary to improve efficiency and effectiveness. Currently, the weights of objective metrics (e.g., wire…

Diversity reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Scalable High-Fidelity Macromolecular Docking for GPU-Accelerated Supercomputers

2026-08-07 · Xiangyu Meng, Peng Chen, Mingzhen Li, Jianmin Wang 외 arxiv

Flexible macromolecular docking offers high-fidelity predictions of biomolecular interactions, but remains prohibitively expensive at scale. Among existing approaches, LightDock leverages Glowworm Swarm Optimization (GSO…

Deep Reinforcement Learning in a Monetary Model

2021-04-19 · Mingli Chen, Andreas Joseph, Michael Kumhof, Xinlei Pan 외

We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic optimisation problem by inte…

Deep Reinforcement Learning model reinforcement-learning Reinforcement Learning+1

Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder

2019-03-22 · Heecheol Kim, Masanori Yamada, Kosuke Miyoshi, Hiroshi Yamakawa

One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimens…

Disentanglement General Reinforcement Learning reinforcement-learning Reinforcement Learning+1